charisma-research-loop

# Charisma Research Loop Use this workflow to avoid shallow repeated advice and continuously improve insight quality. ## Output contract - Produce exactly 5 insights per run. - Make each insight specific, testable, and action-oriented. - Include these fields for each insight: 1) Theme 2) Insight 3) Why it works 4) 24h experiment 5) Failure mode / misuse risk ## Theme rotation Rotate themes so consecutive runs are not repetitive. Use this pool: - Body language and non-verbal signaling - Oration and vocal delivery - Social psychology and status dynamics - Ethical persuasion and influence - Manipulation detection and defense - Conversation architecture and storytelling - Presence under pressure (meetings, conflict, negotiation) ## Source depth rules - Prefer synthesis over quotes. - Pull from mixed source types each run (discussion + educational + behavioral science). - Do not rely on only surface-level generic tips. - Convert raw source material into deeper mechanisms and practical tests. ## Self-improving loop (mandatory) Before generating a new run: 1. Read `/root/.openclaw/workspace/memory/charisma-insight-ledger.md`. 2. Identify what was already sent recently and mark those clusters as `DONE` in today’s section when superseded. 3. Choose at least 3 new angles not used in the most recent 3 runs. 4. Generate the new 5-insight set. 5. Append a compact run log to the ledger: - timestamp - themes used - novelty score (1-10) - repeated ideas avoided - one improvement for next run ## Delivery - Send concise email brief with the 5 insights. - Create/update calendar task/event containing same 5 insights. - Keep wording practical, direct, non-fluffy.